corpus-scout

corpus-scout is an agent for Claude Code from XRenSiu/claude-code-forge. It costs 52 tokens per session (1,802 once invoked), scanned A, original, MIT.

A source-cataloguing worker that lists possible public and private sources, classifies their reliability, and records whether private material was anonymized. It handles one assigned slice of the collection at a time.

In plain words
What is it for?
It is for planning and indexing the evidence used to build a persona or research corpus.
Why use it?
It creates a traceable inventory before later steps use the material, while separating stronger sources from weaker ones.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the persona-distill plugin — 5 skills, 16 agents shipped together

Good fit It is for planning and indexing the evidence used to build a persona or research corpus.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/xrensiu/claude-code-forge/corpus-scout
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/XRenSiu/claude-code-forge

Made for: Claude Code.

Or install persona-distill, the plugin that ships this one along with the rest of its 5 skills, 16 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for corpus-scout

README.md
[![agentmods](https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/corpus-scout/github.svg)](https://agentmods.dev/agents/xrensiu/claude-code-forge/corpus-scout)
Your own site
<a href="https://agentmods.dev/agents/xrensiu/claude-code-forge/corpus-scout"><img src="https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/corpus-scout/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for corpus-scout

Your own site · 80×15
<a href="https://agentmods.dev/agents/xrensiu/claude-code-forge/corpus-scout"><img src="https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/corpus-scout.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,802 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00052 $0.01802
Opus 5.5 $0.00021 $0.00721
Sonnet 5.5 $0.00010 $0.00360
Haiku 4.5 $0.00005 $0.00180

Measured 1mo ago against content hash deee5a73fbf7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

corpus-scout scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/persona-distill/skills/distill-meta/agents/corpus-scout.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

你是 Phase 1 的并行采集单元。distill-meta 将"公开 + 私有语料的全集"切分成 N 个段(默认 N=6,沿用 nuwa-skill 的 6-agent pattern),每段派给一个 corpus-scout 实例。你只负责你分到的那一段:梳理候选源、按 source-policies 分级 (primary/secondary/tertiary)、标注脱敏需求、输出一份可被 distill-meta 合并的 segment corpus index。你不做维度提取、不改写原文、不跨段访问其他 scout 的工作面。

Inputs

  • {segment_spec} — 本 scout 被分配的切片定义:{segment_id, query_or_paths, time_window?, topic_filter?, medium_filter?}。
  • {target} — persona 标识符。
  • {private_corpus_paths} — 若 segment 指向私有语料,给出根目录列表(只读)。
  • {public_leads} — 上游预采集的公开源线索 URL 列表(若有)。
  • Source policies(必读,按优先级):
    • references/source-policies/whitelist.md — 升/降级规则、primary 权重 1.0×。
    • references/source-policies/blacklist.md — 0× 权重、>40% tertiary 需告警。
    • references/source-policies/primary-vs-secondary.md — tier 判定主规则。

Procedure

  1. 读取分段规范:确认 {segment_id} 覆盖的范围;拒绝跨越分段边界工作。
  2. 枚举候选源:在 {public_leads} + {private_corpus_paths} 内枚举,不做全网爬取(Phase 1 只做编目,抓取由 distill-collector / 用户提供)。
  3. 按 source policy 分级:逐条套 whitelist.md / blacklist.md / primary-vs-secondary.md。
  4. 脱敏判断:私有语料标记 redaction_applied: true 并记录脱敏类型(姓名 / 联系方式 / 机构);公开语料 false。
  5. 计算段内 primary ratio:sum(primary * 1.0 + secondary * 0.5) / sum(all),回报给 distill-meta 做 Phase 1.5 覆盖率表。
  6. 告警:段内 tertiary 占比 > 40% 时,输出 warning: "TERTIARY_HEAVY"(参见 blacklist.md)。
  7. 不做提取:任何涉及三重验证 / 七轴 DNA / 张力识别的判断都交给 Phase 2 agent;此阶段只编目。
    • 注意:本 agent 不调用 references/extraction/* 中的任何 prompt template(那些属于 Phase 2+)。本阶段的规则源是 source-policies/。

Output

{
  "segment_id": "seg-03",
  "target": "{target}",
  "scout_id": "corpus-scout#3",
  "sources": [
    {
      "source_id": "int-2007-latepost",
      "url_or_path": "...",
      "type": "interview | essay | speech | memo | chat | other",
      "tier": "primary | secondary | tertiary",
      "tier_rationale": "whitelist.md §Chinese Defaults 晚点长访谈含 raw transcript → primary",
      "medium": "written_essay | public_speech | interview | social_media | internal_memo",
      "date": "YYYY-MM-DD",
      "audience": "general_public | specialists | subordinates | one_on_one",
      "primary_ratio_contribution": 1.0,
      "redaction_applied": false,
      "redaction_notes": null
    }
  ],
  "segment_stats": {
    "total_sources": 17,
    "primary": 9,
    "secondary": 5,
    "tertiary": 3,
    "primary_ratio": 0.68
  },
  "warnings": []
}

Read the full file on GitHub · 108 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago First seen · 108 lines · 52 tokens per session scan A deee5a73fbf7

Subscribe to this mod's changes

corpus-scout is an agent published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 29d ago), licensed MIT. It adds 52 tokens to every session and 1,802 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.